Upload app.py

app.py

@@ -63,38 +63,40 @@ def get_next_row():
         return row
     return pd.DataFrame()
 
-# Feature engineering
-def engineer(df):
-    if pd.api.types.is_numeric_dtype(df["timestamp"]):
-        df["datetime"] = pd.to_datetime(df["timestamp"], unit="s")
-    else:
-        df["datetime"] = pd.to_datetime(df["timestamp"])
-
-    df = df.sort_values("datetime")
-    df["hour_of_day"] = df["datetime"].dt.hour
-    df["lag_30min"] = df["power_consumption_kwh"].shift(1)
-    df["lag_1h"] = df["power_consumption_kwh"].shift(2)
-    df["rolling_avg_1h"] = df["power_consumption_kwh"].rolling(2).mean()
-    df["rolling_avg_2h"] = df["power_consumption_kwh"].rolling(4).mean()
-    df["is_weekend"] = df["datetime"].dt.weekday >= 5
-    df["hour_sin"] = np.sin(2 * np.pi * df["hour_of_day"] / 24)
-    df["hour_cos"] = np.cos(2 * np.pi * df["hour_of_day"] / 24)
-
-    df = pd.get_dummies(df, columns=["property_type", "region"], drop_first=False)
-
-    expected_features = [
-        'lag_30min', 'lag_1h', 'rolling_avg_1h', 'rolling_avg_2h',
-        'hour_of_day', 'is_weekend', 'hour_sin', 'hour_cos',
-        'temperature_c', 'ev_owner', 'solar_installed',
-        'property_type_commercial', 'property_type_residential',
-        'region_north', 'region_south', 'region_east', 'region_west'
-    ]
-
-    for col in expected_features:
-        if col not in df.columns:
-            df[col] = 0
-
-    return df
+
+def forecast_next(df, model, steps=5):
+    forecasts = []
+    df_copy = df.copy()
+    expected_features = model.feature_names_in_.tolist()
+
+    for i in range(steps):
+        df_copy = engineer(df_copy).dropna()
+
+        # Ensure all expected features are present
+        for col in expected_features:
+            if col not in df_copy.columns:
+                df_copy[col] = 0
+
+        # Select and order input features
+        input_row = df_copy.iloc[[-1]][expected_features]
+
+        y_pred = model.predict(input_row)[0]
+
+        # Prepare next row
+        next_timestamp = df_copy.iloc[-1]["timestamp"] + 1800
+        new_row = df_copy.iloc[-1].copy()
+        new_row["power_consumption_kwh"] = y_pred
+        new_row["timestamp"] = next_timestamp
+
+        df_copy = pd.concat([df_copy, pd.DataFrame([new_row])], ignore_index=True)
+        forecasts.append({"timestamp": next_timestamp, "forecast_kwh": y_pred})
+
+    return pd.DataFrame(forecasts)
+
+
+
+
+
 
 # Forecast ahead logic (5 steps, 30min intervals)
 def forecast_next(df, model, steps=5):